Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings最新文献
Pub Date : 2022-10-22DOI: 10.36548/jaicn.2022.3.006
E. Baraneetharan
Most companies nowadays use digital platforms to host conferences, job interviews, and other business events. The unexpected increase in the need for internet platforms has resulted in a rapid rise of fraud advertising. The agencies as well as fraudsters recruit the job seekers using a variety of techniques, including sources from online job-providing websites. By applying Machine Learning algorithms, researchers aim to decrease the number of such fraudulent and fake attempts. In this article, classifiers such as K-Nearest Neighbour, Support Vector Machine, and Extreme Gradient Boosting algorithms are implemented for fake advertisement prediction. The performances of the machine learning algorithms are evaluated using metrics such as accuracy, F1 measures, precision and recall.
{"title":"Detection of Fake Job Advertisements using Machine Learning algorithms","authors":"E. Baraneetharan","doi":"10.36548/jaicn.2022.3.006","DOIUrl":"https://doi.org/10.36548/jaicn.2022.3.006","url":null,"abstract":"Most companies nowadays use digital platforms to host conferences, job interviews, and other business events. The unexpected increase in the need for internet platforms has resulted in a rapid rise of fraud advertising. The agencies as well as fraudsters recruit the job seekers using a variety of techniques, including sources from online job-providing websites. By applying Machine Learning algorithms, researchers aim to decrease the number of such fraudulent and fake attempts. In this article, classifiers such as K-Nearest Neighbour, Support Vector Machine, and Extreme Gradient Boosting algorithms are implemented for fake advertisement prediction. The performances of the machine learning algorithms are evaluated using metrics such as accuracy, F1 measures, precision and recall.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90243841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-15DOI: 10.36548/jaicn.2022.3.008
K. Thangarajan
Heart disease, cancer, renal failure, eye damage, and blindness are just some of the complications that may result from uncontrolled diabetes. Scientists are inspired to develop a Machine Learning (ML) approach for diabetes forecasting. To improve illness diagnosis, medical personnel must make use of ML algorithms. Different ML algorithms for identifying diabetes risk at an early stage are examined and contrasted in this research. The goal in analysing diabetes prediction models is to develop criteria for selecting high-quality studies and synthesising the results from several studies. Nonlinearity, normality, correlation structure, and complexity characterise the vast majority of medical data, making analysis of diabetic data a formidable task. Algorithms based on machine learning are not permitted to be used in healthcare or medical imaging. Early diabetes mellitus prediction necessitates a strategy distinct from those often used. Diabetic patients and healthy individuals may be separated using a risk stratification approach based on machine learning. This study is highly recommended since it reviews a variety of papers that may be used by researchers working on diabetes prediction models.
{"title":"Effective Approach for Early Detection of Diabetes by Logistic Regression through Risk Prediction","authors":"K. Thangarajan","doi":"10.36548/jaicn.2022.3.008","DOIUrl":"https://doi.org/10.36548/jaicn.2022.3.008","url":null,"abstract":"Heart disease, cancer, renal failure, eye damage, and blindness are just some of the complications that may result from uncontrolled diabetes. Scientists are inspired to develop a Machine Learning (ML) approach for diabetes forecasting. To improve illness diagnosis, medical personnel must make use of ML algorithms. Different ML algorithms for identifying diabetes risk at an early stage are examined and contrasted in this research. The goal in analysing diabetes prediction models is to develop criteria for selecting high-quality studies and synthesising the results from several studies. Nonlinearity, normality, correlation structure, and complexity characterise the vast majority of medical data, making analysis of diabetic data a formidable task. Algorithms based on machine learning are not permitted to be used in healthcare or medical imaging. Early diabetes mellitus prediction necessitates a strategy distinct from those often used. Diabetic patients and healthy individuals may be separated using a risk stratification approach based on machine learning. This study is highly recommended since it reviews a variety of papers that may be used by researchers working on diabetes prediction models.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82303554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-15DOI: 10.36548/jaicn.2022.3.007
T. Vijayakumar
Handwritten signature is considered as one of the primary biometric processes for human verification in various applications including banking and legal documentations. In general, the handwritten signatures are verified with respect to the pressure, direction and speed followed on a plain document. However, the traditional methods of verification are less accurate and time consuming. The proposed work aims to develop a deep learning -based approach for handwritten signature verification process through a Modular Neural Network algorithm. The work utilized the handwritten signatures dataset downloaded from the kaggle website that consists of original and forged signatures of 30 individuals. The work also included a set of 20 individual signatures for improving the sample count on training and verification process.
{"title":"Verification System for Handwritten Signatures with Modular Neural Networks","authors":"T. Vijayakumar","doi":"10.36548/jaicn.2022.3.007","DOIUrl":"https://doi.org/10.36548/jaicn.2022.3.007","url":null,"abstract":"Handwritten signature is considered as one of the primary biometric processes for human verification in various applications including banking and legal documentations. In general, the handwritten signatures are verified with respect to the pressure, direction and speed followed on a plain document. However, the traditional methods of verification are less accurate and time consuming. The proposed work aims to develop a deep learning -based approach for handwritten signature verification process through a Modular Neural Network algorithm. The work utilized the handwritten signatures dataset downloaded from the kaggle website that consists of original and forged signatures of 30 individuals. The work also included a set of 20 individual signatures for improving the sample count on training and verification process.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84194030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fiber development in pulp refining can be characterized by three parameters: number of impacts on pulp, N; energy per impact, I, and bar force on fibers, F. These parameters enable comparisons of radically different refining conditions; determination of intensity for hardwoods and softwoods; assessment of effect of bar width on fiber shortening; and predictions of tensile strength increases.
{"title":"Fiber-based characterization of pulp refining","authors":"R. Kerekes, J. D. Macdonald","doi":"10.32964/tj21.9.497","DOIUrl":"https://doi.org/10.32964/tj21.9.497","url":null,"abstract":"Fiber development in pulp refining can be characterized by three parameters: number of impacts on pulp, N; energy per impact, I, and bar force on fibers, F. These parameters enable comparisons of radically different refining conditions; determination of intensity for hardwoods and softwoods; assessment of effect of bar width on fiber shortening; and predictions of tensile strength increases.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85297802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cedric DIFFO TEGUIA, N. Mehr, W. Glasser, P. Stuart
As a result of new lignin extraction plants hatching and increasing volumes of technical lignin becoming available, a variety of lignin derivatives, including phenolic resins and polyurethane (PU) foams, are reaching the marketplace or being used as intermediate products in many industrial applications. In the spectrum of possible lignin derivatives, thermoplastics appear particularly attractive due to a symbiosis of market, policy, and technology drivers. To assess the preferredness for lignin-based thermoplastics, this paper adapted a risk-oriented methodology formerly applied to assess lignin usage in various applications (phenol-formaldehyde [PF] resins, PU foams, and carbon fiber applications) to the case of lignin-based thermoplastics using hydroxypropylated lignin (HPL) and miscible blends of lignin and polyethylene oxide (PEO). The HPL is considered for garbage bags and agricultural films applications, while lignin-PEO blends are used as replacement for acrylonitrile butadiene styrene (ABS) in applications such as automotive parts. In the methodology, two phased-implementation strategies were defined for each thermoplastic derivative, considering perspectives for profit maximization (90 metric tons/day integrated units) and revenue growth (350 metric tons/day overall capacity), which were considered for implementation within a softwood kraft pulping mill. A set of six criteria representative of the main economic and market competitiveness issues were employed, and their respective importance weights were obtained in a multicriteria decision-making (MCDM) panel. Early-stage techno-economic estimates were done as a basis for the calculation of decision criteria. Compared to product derivatives previously assessed, capital investment for thermoplastic strategies appeared marginally higher due to the required lignin modification steps (on average 30% higher at similar capacity, and 6% for higher-scale revenue diversification strategies). Higher operating costs were also observed due to increased chemical expenses for all thermoplastic strategies, which are ultimately balanced by revenues associated with targeted thermoplastic products, leading to greater annual margins and cash flow generation over the project lifetime for thermoplastic strategies compared to other product applications (58% to 66% higher on average, at similar scale). Benefits of improved economics were reflected in economic criteria, internal rate of return (IRR), and cash flow on capital employed (CFCE), as well as in the price competitiveness criterion, CPC. Overall, the combination of relatively high lignin content in the plastic formulation and the less costly modification method contributed to lignin-PEO strategies, gaining the top two rankings. Based on their overall scores, both strategies defined for HPL would also integrate the group of “preferred” strategies, but are outranked by strategies that consider lignin positioning on PU foam applications.
{"title":"Economic and competitive potential of lignin-based thermoplastics using a multicriteria decision-making method","authors":"Cedric DIFFO TEGUIA, N. Mehr, W. Glasser, P. Stuart","doi":"10.32964/tj21.9.479","DOIUrl":"https://doi.org/10.32964/tj21.9.479","url":null,"abstract":"As a result of new lignin extraction plants hatching and increasing volumes of technical lignin becoming available, a variety of lignin derivatives, including phenolic resins and polyurethane (PU) foams, are reaching the marketplace or being used as intermediate products in many industrial applications. In the spectrum of possible lignin derivatives, thermoplastics appear particularly attractive due to a symbiosis of market, policy, and technology drivers. \u0000To assess the preferredness for lignin-based thermoplastics, this paper adapted a risk-oriented methodology formerly applied to assess lignin usage in various applications (phenol-formaldehyde [PF] resins, PU foams, and carbon fiber applications) to the case of lignin-based thermoplastics using hydroxypropylated lignin (HPL) and miscible blends of lignin and polyethylene oxide (PEO). The HPL is considered for garbage bags and agricultural films applications, while lignin-PEO blends are used as replacement for acrylonitrile butadiene styrene (ABS) in applications such as automotive parts. In the methodology, two phased-implementation strategies were defined for each thermoplastic derivative, considering perspectives for profit maximization (90 metric tons/day integrated units) and revenue growth (350 metric tons/day overall capacity), which were considered for implementation within a softwood kraft pulping mill. A set of six criteria representative of the main economic and market competitiveness issues were employed, and their respective importance weights were obtained in a multicriteria decision-making (MCDM) panel.\u0000Early-stage techno-economic estimates were done as a basis for the calculation of decision criteria. Compared to product derivatives previously assessed, capital investment for thermoplastic strategies appeared marginally higher due to the required lignin modification steps (on average 30% higher at similar capacity, and 6% for higher-scale revenue diversification strategies). Higher operating costs were also observed due to increased chemical expenses for all thermoplastic strategies, which are ultimately balanced by revenues associated with targeted thermoplastic products, leading to greater annual margins and cash flow generation over the project lifetime for thermoplastic strategies compared to other product applications (58% to 66% higher on average, at similar scale). Benefits of improved economics were reflected in economic criteria, internal rate of return (IRR), and cash flow on capital employed \u0000(CFCE), as well as in the price competitiveness criterion, CPC. Overall, the combination of relatively high lignin content in the plastic formulation and the less costly modification method contributed to lignin-PEO strategies, gaining the top two rankings. Based on their overall scores, both strategies defined for HPL would also integrate the group of “preferred” strategies, but are outranked by strategies that consider lignin positioning on PU foam applications.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72699358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Paper industries are facing a raw material crisis and searching for alternate raw materials that may be able to help mitigate the issue. Many industries use agro-waste as a raw material, irrespective of it having low bleachability and poor mechanical strength. Areca nut leaf (ANL) is a nonwood-based material that may be acceptable as an alternate source of raw material that contains 61.5% holocellulose and 13.6% lignin, which is comparable to other agro-wastes and hardwood pulps. Kraft anthraquinone pulping with 20% active alkali as sodium oxide (Na2O), 25% sulfidity, and 0.05% anthraquinone produced 15 kappa pulps with about 38.5% pulping yield. The bleachability of ANL pulp was good, and 83.5% ISO brightness could be achieved using the D0(EOP)D1 bleaching sequence. The ANL fiber has 33.8% better tensile, 54.5% better tear, and 15.2% better burst index than hardwood fiber. Similarly, 60.4% better tensile, 56.5% better tear, and 21.7% better burst index were observed in ANL than in wheat straw. Thus, the study revealed that Areca nut leaf can be used as an alternative raw material for papermaking, as well as to improve the physical property of paper products by blending it with inferior quality pulp.
{"title":"Development of reinforced paper and mitigation of the challenges of raw material availability by utilizing Areca nut leaf","authors":"Kishan Jaishwal, Izhar Alam, C. Sharma","doi":"10.32964/tj21.9.469","DOIUrl":"https://doi.org/10.32964/tj21.9.469","url":null,"abstract":"Paper industries are facing a raw material crisis and searching for alternate raw materials that may be able to help mitigate the issue. Many industries use agro-waste as a raw material, irrespective of it having low bleachability and poor mechanical strength. \u0000Areca nut leaf (ANL) is a nonwood-based material that may be acceptable as an alternate source of raw material that contains 61.5% holocellulose and 13.6% lignin, which is comparable to other agro-wastes and hardwood pulps. \u0000Kraft anthraquinone pulping with 20% active alkali as sodium oxide (Na2O), 25% sulfidity, and 0.05% anthraquinone produced 15 kappa pulps with about 38.5% pulping yield. The bleachability of ANL pulp was good, and 83.5% ISO brightness could be achieved using the D0(EOP)D1 bleaching sequence. The ANL fiber has 33.8% better tensile, 54.5% better tear, and 15.2% better burst index than hardwood fiber. Similarly, 60.4% better tensile, 56.5% better tear, and 21.7% better burst index were observed in ANL than in wheat straw. Thus, the study revealed that Areca nut leaf can be used as an alternative raw material for papermaking, as well as to improve the physical property of paper products by blending it with inferior quality pulp.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80945078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Three factors are involved in cellulose bonding--available area, contact, and hydrogen bonding.
纤维素结合涉及三个因素——可用面积、接触和氢键。
{"title":"The Mechanism of Bonding","authors":"W. Campbell","doi":"10.32964/tj42.12.999","DOIUrl":"https://doi.org/10.32964/tj42.12.999","url":null,"abstract":"Three factors are involved in cellulose bonding--available area, contact, and hydrogen bonding.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91492426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-28DOI: 10.36548/jitdw.2022.3.008
S. S. Sivaraju, C. Kumar
Energy efficiency is one of the primary requirements for designing a successful Wireless Sensor Network (WSN) model. The WSN systems are generally made with a group of nodes that are operated with a small size battery device. To improve the energy efficiency of such WSNs several methodologies like clustering approach, mobile node technique and optimal route planning designs were developed. Scheduling method is yet an efficient model that is widely used in WSN applications, that allows the nodes to be operated only for a certain prescribed time. The proposed work utilizes the Self Organizing Maps (SOM) approach for improving the performances of the scheduling algorithms to a certain limit. SOM is a kind of artificial neural network that analyzes the problem based on competitive learning rather than the backpropagation methods. The work compares the proposed algorithm with the traditional Ant Colony and Software Defined Network approaches, wherein the proposed approach has shown an improvement in terms of energy conservation and network lifetime.
{"title":"Energy Enhancement of WSN with Deep Learning based SOM Scheduling Algorithm","authors":"S. S. Sivaraju, C. Kumar","doi":"10.36548/jitdw.2022.3.008","DOIUrl":"https://doi.org/10.36548/jitdw.2022.3.008","url":null,"abstract":"Energy efficiency is one of the primary requirements for designing a successful Wireless Sensor Network (WSN) model. The WSN systems are generally made with a group of nodes that are operated with a small size battery device. To improve the energy efficiency of such WSNs several methodologies like clustering approach, mobile node technique and optimal route planning designs were developed. Scheduling method is yet an efficient model that is widely used in WSN applications, that allows the nodes to be operated only for a certain prescribed time. The proposed work utilizes the Self Organizing Maps (SOM) approach for improving the performances of the scheduling algorithms to a certain limit. SOM is a kind of artificial neural network that analyzes the problem based on competitive learning rather than the backpropagation methods. The work compares the proposed algorithm with the traditional Ant Colony and Software Defined Network approaches, wherein the proposed approach has shown an improvement in terms of energy conservation and network lifetime.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78385115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The skin acts as a conduit between the brain and the outside environment. The information it receives, such as a touch on the shoulder or the heat from a fire, is processed and used to choose an appropriate response by the brain. A skin functionality may be achieved by incorporating sensors onto bionic skins that are on par with the sensitivity of biological skins. However, doing so is not simple. Recent developments in physiological sensing, sensory perception, and virtual and augmented reality are discussed, as are other intelligent uses of skin-integrated electronics. These skin-integrated systems are advancing the materials and structural designs necessary for the next generation of electronic eyes, ears, and skin. Future progress in this area of study will be aided by interdisciplinary exploration into fields such as materials science, electrical engineering, mechanics, and biomedical engineering.
{"title":"Miniaturized Skin-Integrated Electronics in Real Time for Virtual Assistance - A Review","authors":"T. Senthilkumar, Anuradha Thangavelu","doi":"10.36548/jei.2022.3.008","DOIUrl":"https://doi.org/10.36548/jei.2022.3.008","url":null,"abstract":"The skin acts as a conduit between the brain and the outside environment. The information it receives, such as a touch on the shoulder or the heat from a fire, is processed and used to choose an appropriate response by the brain. A skin functionality may be achieved by incorporating sensors onto bionic skins that are on par with the sensitivity of biological skins. However, doing so is not simple. Recent developments in physiological sensing, sensory perception, and virtual and augmented reality are discussed, as are other intelligent uses of skin-integrated electronics. These skin-integrated systems are advancing the materials and structural designs necessary for the next generation of electronic eyes, ears, and skin. Future progress in this area of study will be aided by interdisciplinary exploration into fields such as materials science, electrical engineering, mechanics, and biomedical engineering.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78712634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-19DOI: 10.36548/jitdw.2022.3.007
Prabin Acharya, S. Shakya
In Nepali language, compound word formation is mostly associated with inflection, derivation, and postposition attachment. Inflection occurs due to suffixation, whereas derivation is driven by both prefixation and suffixation. The compound word generated by the rules may produce lots of out-of-vocabulary words due to limited lexical resources and numerous exceptions. Hence, the machine learning approach can help to generate valid compounds and split them into valid morphemes that can be further used as a resource for spelling suggestions, information retrieval, and machine translation. In this research, a method to generate valid compounds from the corresponding compound splits (head word and prefix/suffix/ postpositions) is suggested. A BiLSTM based deep learning approach was used to generate and split the valid compound words. Publicly available Nepali Brihat Shabdakosh data from Nepal Academy and scraped news data were used for the experimentation. The obtained results were found to be outstanding compared to the rule-based approach applied to a similar job.
{"title":"Generation and Splitting of the Compound Words in Nepali Text","authors":"Prabin Acharya, S. Shakya","doi":"10.36548/jitdw.2022.3.007","DOIUrl":"https://doi.org/10.36548/jitdw.2022.3.007","url":null,"abstract":"In Nepali language, compound word formation is mostly associated with inflection, derivation, and postposition attachment. Inflection occurs due to suffixation, whereas derivation is driven by both prefixation and suffixation. The compound word generated by the rules may produce lots of out-of-vocabulary words due to limited lexical resources and numerous exceptions. Hence, the machine learning approach can help to generate valid compounds and split them into valid morphemes that can be further used as a resource for spelling suggestions, information retrieval, and machine translation. In this research, a method to generate valid compounds from the corresponding compound splits (head word and prefix/suffix/ postpositions) is suggested. A BiLSTM based deep learning approach was used to generate and split the valid compound words. Publicly available Nepali Brihat Shabdakosh data from Nepal Academy and scraped news data were used for the experimentation. The obtained results were found to be outstanding compared to the rule-based approach applied to a similar job.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77262881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：